differential-dynamic-programming

Fast and embedded solvers for nonlinear optimal control and nonlinear model predictive control

Crocoddyl is an optimal control library for robot control under contact sequence. Its solver is based on various efficient Differential Dynamic Programming (DDP)-like algorithms

Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models

iterative Linear Quadratic Regulator with support for constraints on input and state variables via barrier functions—Numba-accelerated.

Differential Dynamic Programming controller operating in OpenAI Gym environment.

Differential Dynamic Programming (DDP) with automatic symbolic differentiation

Constrained Differential Dynamic Programming Solver for Trajectory Optimization and Model Predictive Control

A toolbox for trajectory optimization of dynamical systems

A Julia package for constrained iterative LQR (iLQR)

Code supporting the WAFR paper "A Performance Analysis of Differential Dynamic Programming on a GPU," and the ICRA workshop follow on work deploying the algorithm onto robot hardware.

Project management and files related to my master's thesis on 'Highly-Dynamic Movements of a Humanoid Robot Using Whole-Body Trajectory Optimization'

WIP implementation of Probabilistic Differential Dynamic Programming in PyTorch

Differential Dynamic Programming python implementation for a cartpole system

Implementation of DDP algorithm for Optimal Control on a Bicycle Model for optimal lane change maneuvering and Skidpad track following.

Optimal control solver implemented in Python. SymPy for symbolic differentiation and Numba for fast computation.

Design of a Differential dynamic programming (DDP) algorithm for the optimal control of a Ball and Beam system

Guided policy search in Python and ROS Indigo.

Constrained DDP and dynamic-programming code for lane-free automated-vehicle path planning.